© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5970
    Prev
    Next
    INDEX
    Explanations

    expressions of assertions, claims, allegations, or suggestions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.93
    AddTagHelper
    -0.90
    mybatisplus
    -0.85
    jsxFileName
    -0.78
     ligiloj
    -0.76
    enosine
    -0.72
    UnusedPrivate
    -0.72
    CascadeType
    -0.69
    AutoScale
    -0.69
     nakalista
    -0.69
    POSITIVE LOGITS
     suggestion
    0.90
     allegation
    0.90
     assertion
    0.86
     assumption
    0.82
     hypothesis
    0.79
     supposition
    0.78
     criticisms
    0.78
     allegations
    0.74
     assertions
    0.73
     criticism
    0.71
    Activations Density 1.035%

    No Known Activations